Search

IEEE 802.11ax is the standard for the new generation WiFi networks. In this paper, we formulate the problem of joint access point (AP) placement and power-channel-resource unit assignment for 802.11ax-based dense WiFi. The objective is to minimize the number of APs. Two quality-of-service (QoS) requirements are to be fulfilled: (1) a two-tier throughput requirement which ensures that the throughput of each station is good enough, and (2) a fault tolerance requirement which ensures that the stations could still use WiFi even when some APs fail. We prove that this problem is NP-hard. To tackle this problem, we first develop an analytic model to derive the throughput of each station under the OFDMA mechanism and a widely used interference model. We then design a heuristic algorithm to find high-quality solutions with polynomial time complexity. Simulation results under both fixed-user and mobile-user cases show that: (1) when the area is small (50 x 50 m2), our algorithm gives the optimal solutions; when the area is larger (80 x 60 m2), our algorithm can reduce the number of APs by 34.9-87.7% as compared to the Random and Greedy algorithms. (2) Our algorithm can always get feasible solutions that fulfill the QoS requirements.

Projection techniques are often used to visualize high-dimensional data, allowing users to better understand the overall structure of multi-dimensional spaces on a 2D screen. Although many such methods exist, comparably little work has been done on generalizable methods of inverse-projection -- the process of mapping the projected points, or more generally, the projection space back to the original high-dimensional space. In this paper we present NNInv, a deep learning technique with the ability to approximate the inverse of any projection or mapping. NNInv learns to reconstruct high-dimensional data from any arbitrary point on a 2D projection space, giving users the ability to interact with the learned high-dimensional representation in a visual analytics system. We provide an analysis of the parameter space of NNInv, and offer guidance in selecting these parameters. We extend validation of the effectiveness of NNInv through a series of quantitative and qualitative analyses. We then demonstrate the method's utility by applying it to three visualization tasks: interactive instance interpolation, classifier agreement, and gradient visualization.

Identifying geometric features from sampled surfaces is a significant and fundamental task. The existing curvature-based methods that can identify ridge and valley features are generally sensitive to noise. Without requiring high-order differential operators, most statistics-based methods sacrifice certain extents of the feature descriptive powers in exchange for robustness. However, neither of these types of methods can treat the surface boundary features simultaneously. In this paper, we propose a novel neighbor reweighted local centroid (NRLC) computational algorithm to identify geometric features for point cloud models. It constructs a feature descriptor for the considered point via decomposing each of its neighboring vectors into two orthogonal directions. A neighboring vector starts from the considered point and ends with the corresponding neighbor. The decomposed neighboring vectors are then accumulated with different weights to generate the NRLC. With the defined NRLC, we design a probability set for each candidate feature point so that the convex, concave and surface boundary points can be recognized concurrently. In addition, we introduce a pair of feature operators, including assimilation and dissimilation, to further strengthen the identified geometric features. Finally, we test NRLC on a large body of point cloud models derived from different data sources. Several groups of the comparison experiments are conducted, and the results verify the validity and efficiency of our NRLC method.

The grid-based approach is popular for point-in-polygon tests. However, there is a trade-off between the preprocessing and the inclusion test, which always requires the grid resolutions to be tuned. In this article, we address this challenge by enhancing the grid structure using y-axis-aligned stripes, which are formed by the y-axis-aligned lines passing through the endpoints of the edge segments in the cell, thereby managing the edge segments in each grid cell. Moreover, we precompute the inclusion properties of the x-axis-aligned top borders of the stripes during preprocessing. Therefore, to answer a query point with the ray crossing method, we can emit a ray from the point to propagate upwards until the ray arrives at the top border of a stripe. We thoroughly consider singular cases to guarantee each query point can be answered in the stripe that contains the point. In our method, the computational load can be decreased, as one coordinate of the intersection point between the ray and an edge is known in advance, and parallel computing can be well exploited because the branching operations for determining whether an edge intersects with the ray are saved. Experimental results show that the efficiency of our method does not vary much with respect to the grid resolutions, so the trouble of tuning grid resolutions can be avoided. Ultimately, our method with a low grid resolution can reduce the preprocessing time and still achieve a higher inclusion test efficiency than the existing methods with a high grid resolution, especially on GPUs.

Ships are usually disturbed by waves when they are traveling at sea. When the waves are large, it is not conducive to driving safety, comfort and economy. Therefore, this paper proposed a new type of automatic driving scheme, which links the wave height prediction with ship driving. By studying the accurate prediction of wave height, ships can adjust their course in real time to ensure that they always travel in the area with the lowest wave height. According to the different driving conditions of ships in the open sea and the offshore sea, we designed two wave height prediction models based on LSTM, which are suitable for the above two types of sea areas. In particular, when we created the open sea model, we selected the data of the location points other than the predicted point as the training data. After comparative testing, the two types of models have reached satisfactory accuracy, which provided support for the ship automatic driving scheme proposed in this paper.

Knee points, characterized as a small improvement on one objective can lead to a significant degradation on at least one of the other objectives, are attractive to decision makers in multi-criterion decision-making. This paper presents a simple and effective knee point identification method to help decision makers identify solution(s) of interest from a given set of trade-off solutions thus facilitating posterior decision-making. Our basic idea is to sequentially validate whether a solution is a knee point or not by comparing its localized trade-off utility with others within its neighborhood characterized from a decomposition perspective. In particular, a solution is a knee point if and only if it has the best localized trade-off utility among its neighbors. We implement a GPU version that carries out the knee point identification in a parallel manner. This GPU version reduces the worst-case complexity from quadratic to linear. The performance of our proposed method is compared with five state-of-the-art knee point identification methods on 134 test problem instances and two real-world engineering design problems. Empirical results demonstrate its outstanding performance especially on problems with many local knee points. We further validate the usefulness of our proposed method for guiding evolutionary multi-objective optimization algorithms to search for knee points on the fly during the evolutionary process.

With increasing of data size and development of multi-core computers, asynchronous parallel stochastic optimization algorithms such as KroMagnon have gained significant attention. In this paper, we propose a new Sparse approximation and asynchronous parallel Stochastic Variance Reduced Gradient (SSVRG) method for sparse and high-dimensional machine learning problems. Unlike standard SVRG and its asynchronous parallel variant, KroMagnon, the snapshot point of SSVRG is set to the average of all the iterates in the previous epoch, which allows it to take much larger learning rates and makes it more robust to the choice of learning rates. In particular, we use the sparse approximation of the popular SVRG estimator to perform completely sparse updates. Therefore, SSVRG has a much lower per-iteration computational cost than its dense counterpart, SVRG++, and is very friendly to asynchronous parallel implementation. Moreover, we provide the convergence guarantees of SSVRG for both SC and non-SC problems, while existing asynchronous algorithms (e.g., KroMagnon) only have convergence guarantees for SC problems. Finally, we extend SSVRG to non-smooth and asynchronous parallel settings. Numerical results demonstrate that SSVRG converges significantly faster than the state-of-the-art asynchronous parallel methods, e.g., KroMagnon, and is usually more than three orders of magnitude faster than SVRG++.

In this paper, we explore the mask representation in instance segmentation with Point-of-Interest (PoI) features. Differentiating multiple potential instances within a single PoI feature is challenging because learning a high-dimensional mask feature for each instance using vanilla convolution demands a heavy computing burden. To address this challenge, we propose an instance-aware convolution. It decomposes this mask representation learning task into two tractable modules as instance-aware weights and instance-agnostic features. The former is to parametrize convolution for producing mask features corresponding to different instances, improving mask learning efficiency by avoiding employing several independent convolutions. Meanwhile, the latter serves as mask templates in a single point. Together, instance-aware mask features are computed by convolving the template with dynamic weights, used for the mask prediction. Along with instance-aware convolution, we propose PointINS, a simple and practical instance segmentation approach, building upon dense one-stage detectors. Through extensive experiments, we evaluated the effectiveness of our framework built upon RetinaNet and FCOS. PointINS in ResNet101 backbone achieves a 38.3 mask mean average precision (mAP) on COCO dataset, outperforming existing point-based methods by a large margin. It gives a comparable performance to the region-based Mask R-CNN with faster inference., Comment: Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence

An effective path-following guidance algorithm for unmanned combat aerial vehicles by pursuing a look-ahead target-point along the desired path is devised. The concept of look-ahead pursuit for 3-D path-following was extended from the planar ${\mathcal {L}_1}$ guidance, which has been widely adopted in the application of lateral guidance of fixed-wing drone. Decoupled implementation of the planar guidance action on each of the longitudinal (vertical) and lateral (horizontal) planes supplies longitudinal-lateral acceleration commands in two perpendicular planes which is well accepted by aviation engineers. The computation of the look-ahead point utilizes a finite and iterative numerical search method by introducing an auxiliary path-related parameter. Furthermore, additional implementation-specific details such as the modification of adaptive ${\mathcal {L}_1}$ length and the protection strategies ensuring wide applicability of the algorithm indeed guarantee certain necessity to be considered in real implementation of the guidance law. The improved schemes eliminate complicated coordinate transformations and are built on the path-independent assumption, thus making them easier to be adjusted between various types of paths, including discrete optimal trajectories. Monte Carlo simulations and real-world flight tests have confirmed the effectiveness of the nonlinear guidance algorithm.

In medical image analysis (MIA) and computer-assisted surgery (CAS), aligning two multiple point sets (PSs) together is an essential but also a challenging problem. For example, rigidly aligning multiple point sets into one common coordinate frame is a prerequisite for statistical shape modelling (SSM). Accurately aligning the pre-operative space with the intra-operative space in CAS is very crucial to successful interventions. In this article, we formally formulate the multiple generalized point set registration problem (MGPSR) in a probabilistic manner, where both the positional and the normal vectors are used. The six-dimensional vectors consisting of both positional and normal vectors are called as generalized points. In the formulated model, all the generalized PSs to be registered are considered to be the realizations of underlying unknown hybrid mixture models (HMMs). By assuming the independence of the positional and orientational vectors (i.e., the normal vectors), the probability density function (PDF) of an observed generalized point is computed as the product of Gaussian and Fisher distributions. Furthermore, to consider the anisotropic noise in surgical navigation, the positional error is assumed to obey a multi-variate Gaussian distribution. Finally, registering PSs is formulated as a maximum likelihood (ML) problem, and solved under the expectation maximization (EM) technique. By using more enriched information (i.e., the normal vectors), our algorithm is more robust to outliers. By treating all PSs equally, our algorithm does not bias towards any PS. To validate the proposed approach, extensive experiments have been conducted on surface points extracted from CT images of (i) a human femur bone model; (ii) a human pelvis bone model. Results demonstrate our algorithm's high accuracy, robustness to noise and outliers.

Most supervised learning-based pose estimation methods for stacked scenes are trained on massive synthetic datasets. In most cases, the challenge is that the learned network on the training dataset is no longer optimal on the testing dataset. To address this problem, we propose a pose regression network PPR-Net++. It transforms each scene point into a point in the centroid space, followed by a clustering process and a voting process. In the training phase, a mapping function between the network's critical parameter (i.e., the bandwidth of the clustering algorithm) and the compactness of the centroid distributions is obtained. This function is used to adapt the bandwidth between centroid distributions of two different domains. In addition, to further improve the pose estimation accuracy, the network also predicts the confidence of each point, based on its visibility and pose error. Only the points with high confidence have the right to vote for the final object pose. In experiments, our method is trained on the IPA synthetic dataset and compared with the state-of-the-art algorithm. When tested with the public synthetic Sileane dataset, our method is better in all eight objects, where five of them are improved by more than 5% in average precision (AP). On IPA real dataset, our method outperforms a large margin by 20%. This lays a solid foundation for robot grasping in industrial scenarios.

In modern discrete flexible manufacturing systems, dynamic disturbances frequently occur in real time and each job may contain several special operations in partial-no-wait constraint due to technological requirements. In this regard, a hierarchical multiagent deep reinforcement learning (DRL)-based real-time scheduling method named hierarchical multi-agent proximal policy optimization (HMAPPO) is developed to address the dynamic partial-no-wait multiobjective flexible job shop scheduling problem (DMOFJSP-PNW) with new job insertions and machine breakdowns. The proposed HMAPPO contains three proximal policy optimization (PPO)-based agents operating in different spatiotemporal scales, namely, objective agent, job agent, and machine agent. The objective agent acts as a higher controller periodically determining the temporary objectives to be optimized. The job agent and machine agent are lower actuators, respectively, choosing a job selection rule and machine assignment rule to achieve the temporary objective at each rescheduling point. Five job selection rules and six machine assignment rules are designed to select an uncompleted job and assign the next operation of which together with its successors in no-wait constraint on the corresponding processing machines. A hierarchical PPO-based training algorithm is developed. Extensive numerical experiments have confirmed the effectiveness and superiority of the proposed HMAPPO compared with other well-known dynamic scheduling methods.

In this article, a novel method for simultaneous localization and mapping (SLAM) named surface elements (surfel) point SLAM (SP-SLAM) is proposed using an RGB-D camera. The key idea of SP-SLAM is to use not only keypoints but also surfels as features to cope with both high texture and low texture environments. By decomposing a surface into a small number of surfels, the method can represent spacious environments using a relatively small amount of memory. To optimize the poses of points, surfels, and cameras altogether, new objective functions are proposed, and a new bundle adjustment using these objective functions is developed. The proposed SP-SLAM runs in real time on a central processing unit as in other feature-based visual SLAM methods but works better than them not only in high texture but also in low texture environments, overcoming well-known drawbacks of feature-based visual SLAM with degradation in low texture environments. The proposed method is applied to benchmark datasets and its effectiveness is demonstrated by comparing against those of previous methods in terms of localization accuracy.

With the increasing penetration of wind power generation, the fluctuating and intermittent behavior of wind power poses huge challenges to the operation and planning of distribution networks. A popular way to mitigate these challenges is to provide a group of possible wind power forecasting scenarios instead of depending on deterministic point forecasting values, so that system operators can consider the uncertainties. This letter proposes a novel WindGMMN method for wind power scenario forecasting, in which necessary modifications are made on the generative moment matching network (GMMN), and an optimization strategy is designed to find a series of wind power scenarios with similar shapes, probability distributions, and temporal correlations as potential scenarios. Simulations and analyses were performed on a public dataset with 2190 wind power generation curves and their corresponding meteorological features. The results show that the proposed WindGMMN outperforms popular baselines (e.g., variational auto-encoders and generative adversarial networks) for scenario forecasting of wind power, without any restrictions on the time horizon (e.g., times ranging from 10 min to 24 h).

Snake robots have shown limited ability to perform manipulation tasks in comparison to their locomotion capabilities. In this article, we propose a mobile manipulation approach that increases the manipulation ability of snake robots by using their full-body motion. We consider a snake robot that moves along the outer surface of a pipe using the helical rolling gait. To perform a manipulation task, we extend the front links of the robot to form a manipulator-part, where the remaining links form a helical base that wraps around the pipe. In the proposed approach, the motion of the manipulator-part is combined with a rolling motion performed by the base-part. This results in enhanced rotational ability of the end-effector, without the need to install an additional rotary motor. The stability of the robot structure is also improved via the resulting tightening force between the helical base-part and the pipe. The kinematics of the proposed robot arrangement is represented considering a dynamically changing contact point between the links of the helical base and the pipe. To realize the proposed method, we introduce a two-level controller that enables the manipulator-part and the helical base to work simultaneously during manipulation. The experimental results showed the validity of the proposed method to track various trajectories and carry out manipulation tasks using a typical snake robot without extra actuators.

Sintering is the preproduction process of ironmaking, whose products are the basis of ironmaking. How to improve the operating performance of the iron ore sintering process has always been a problem that operators are committed to solve. An operating performance improvement method based on prediction and grade assessment is presented in this article. First, considering the data distribution characteristics of the process, a performance index prediction model based on the Gaussian process regression is built, in which the mutual information analysis method is used to select the inputs of the performance index prediction model. Then, the operating performance grade is assessed by a threshold division method. Next, the operating performance grade guides the control of the burn-through point to improve the operating performance. Finally, experimental verification is performed based on the actual running data. The results show that the proposed method has high prediction accuracy, and it is also significant in improving the operating performance. Therefore, this approach provides an effective solution to predict and improve operating performance.

We investigate the implementation of a sparsity promoting hands-off control scheme using the alternating direction method of multiplies (ADMM). In order to minimize the numerical control effort along with the actuation one, only a single ADMM iteration per time step is considered. We analyze the resulting closed-loop dynamics for linear systems with additive disturbances and show that the proposed scheme provides sparse controls as desired and, in addition, ensures input-to-state practical stability. We further point out a close relation between the proposed real-time scheme and (non-minimum time) dead-beat control. Finally, characteristics and effectiveness of the novel hands-off controller(s) are illustrated with numerical examples.

The SLAM problem in dynamic scenes is regarded as a challenge. This article proposes a novel SLAM framework for dynamic environments, which combines neural network and motion information of dynamic objects, making the system more adaptable to dynamic scenes. Specifically, we adopt a fast object detection network, tightly couple the results of the object detection with the geometric information in the SLAM system. Then the feature point extracted from the image is associated with a dynamic probability. By utilizing the feature points which tend to be static, the localization result can be greatly improved in dynamic environments. We perform the experiments both on the public data set and the real environment. The result can demonstrate that the proposed method greatly improves the localization accuracy in a dynamic environment. An open-source version of the source code is available.

In recent years, the proximal policy optimization (PPO) algorithm has received considerable attention because of its excellent performance in many challenging tasks. However, there is still a large space for theoretical explanation of the mechanism of PPO's horizontal clipping operation, which is a key means to improve the performance of PPO. In addition, while PPO is inspired by the learning theory of trust region policy optimization (TRPO), the theoretical connection between PPO's clipping operation and TRPO's trust region constraint has not been well studied. In this article, we first analyze the effect of PPO's clipping operation on the objective function of conservative policy iteration, and strictly give the theoretical relationship between PPO and TRPO. Then, a novel first-order policy gradient algorithm called authentic boundary PPO (ABPPO) is proposed, which is based on the authentic boundary setting rule. To ensure the difference between the new and old policies is better kept within the clipping range, by borrowing the idea of ABPPO, we proposed two novel improved PPO algorithms called rollback mechanism-based ABPPO (RMABPPO) and penalized point policy difference-based ABPPO (P3DABPPO), which are based on the ideas of rollback clipping and penalized point policy difference, respectively. Experiments on the continuous robotic control tasks implemented in MuJoCo show that our proposed improved PPO algorithms can effectively improve the learning stability and accelerate the learning speed compared with the original PPO.

In this article, we introduce interval-valued Kuhn-Tucker (KT)-pseudoinvex optimization problems governed by interval-valued path-independent curvilinear integral objective functionals. Concretely, it is proven that an interval-valued KT-pseudoinvex variational control problem is described such that every KT point is an LU-optimal solution. In addition, the main results are highlighted by two illustrative applications describing the controlled behavior of an artificial neural system.

Adaptive output-feedback consensus with funnel performance is studied for nonlinear uncertain multi-agent systems (MASs). The nonlinear MASs contain unknown dynamics and only an output variable can be measured. The other states are not measured directly and are reconstructed via fuzzy state observers. The presence of output feedback makes the proposed design significantly different from the existing literature on control with funnel performance. In particular, appropriate adaptive laws must be defined to handle the presence of uncertain dynamics and local output information from a few neighboring nodes. Interestingly, with a suitable error transformation, it is shown that the proposed control law has a simpler structure than barrier function methods proposed in the literature to handle funnel-like performance. With respect to this point, simulation studies illustrate that the proposed method can dramatically reduce the control effort while satisfying transient and steady-state performance imposed by the funnel.

In this article, a novel interval type-2 Takagi-Sugeno fuzzy c -regression modeling method with a modified distance definition is proposed. The modified distance definition is developed to describe the distance between each data point and the local type-2 fuzzy model. To improve the robustness of the proposed identification method, a modified objective function is presented. In addition, different from most previous studies that require numerous free parameters to be determined, an interval type-2 fuzzy c -regression model is developed to reduce the number of such free parameters. Furthermore, an improved ratio between the upper and lower weights is proposed based on the upper and lower membership function with each input data, and the ordinary least-squares method is adopted to establish the type-2 fuzzy model. The Box-Jenkins model and two numerical models are given to illustrate the effectiveness and robustness of the proposed results.

Finite control-set model predictive control (FCS-MPC) shows superior dynamic performance with simple structure for motor drives. However, conventional FCS-MPC method presents unfixed switching frequency, making it intractable for the design of heat sinks and output filters. To address this issue, this study is devoted to developing a new FCS-MPC strategy with constant switching frequency for permanent magnet synchronous motor (PMSM) drives fed by three-level T-type inverter. The switching frequency regulation is realized by extending the period control technique, where the periods are measured between each rising edge and falling edge of the gate signals. The proposed algorithm can be embedded in the iterative process of the FCS-MPC, which can easily achieve the fixed switching frequency with balanced neutral point potential. The performance of this control strategy is numerically evaluated and experimentally verified by an 11-kW PMSM drive platform.

Multi-dimensional range queries, especially over the cloud platform, have received considerable attention in recent years. However, as the cloud server is not fully trustable, designing multi-dimensional range queries over encrypted data becomes a research trend, and many solutions have been proposed in the literature. Nevertheless, most existing solutions suffer from the leakage of single-dimensional privacy. Although a few existing works have addressed the problem of single-dimensional privacy, they are impractical in some real scenarios due to the issues of inefficiency, inaccuracy, and two-cloud-server requirement. Aiming at solving these issues, in this paper, we propose a practical and privacy-preserving multi-dimensional range query (PRQ) scheme. Specifically, in our PRQ scheme, we first index the multi-dimensional database with an R-tree and reduce R-tree based range queries to the problem of point intersection and range intersection. Then, by employing the lightweight matrix encryption technique, we design two novel algorithms for PRQ, i.e., multi-dimensional point intersection predicate encryption (PIPE) and multi-dimensional range intersection predicate encryption (RIPE), which can preserve the privacy of the proposed point intersection algorithm and range intersection algorithm, and further preserve the single-dimensional privacy in the PRQ scheme. Security analysis and extensive simulations show that our PRQ scheme is privacy-preserving and efficient.

In molecular analysis, Spatial Distribution Functions (SDF) are fundamental instruments in answering questions related to spatial occurrences and relations of atomic structures over time. Given a molecular trajectory, SDFs can, for example, reveal the occurrence of water in relation to particular structures and hence provide clues of hydrophobic and hydrophilic regions. For the computation of meaningful distribution functions, the definition of molecular reference structures is essential. Therefore we introduce the concept of an internal frame of reference (IFR) for labeled point sets that represent selected molecular structures, and we propose an algorithm for tracking the IFR over time and space using a variant of Kabschs algorithm. This approach lets us generate a consistent space for the aggregation of the SDF for molecular trajectories and molecular ensembles. We demonstrate the usefulness of the technique by applying it to temporal molecular trajectories as well as ensemble datasets. The examples include different docking scenarios with DNA, insulin, and aspirin. Funding agencies:This work was supported through grants from the ExcellenceCenter at Link¨oping and Lund in Information Technology(ELLIIT) and the Swedish e-Science Research Centre(SeRC). The authors thanks the Swedish National Infrastructurefor Computing (SNIC) for providing computingresources.

The topology of isosurfaces changes at isovalues of critical points, making such points an important feature when building contour trees or Morse-Smale complexes. Hexahedral elements with linear interpolants can contain additional off-vertex critical points in element bodies and on element faces. Moreover, a point on the face of a hexahedron which is critical in the element-local context is not necessarily critical in the global context. In ‘`Exploring Scalar Fields Using Critical Isovalues’' Weber et al. introduce a method to determine whether critical points on faces are also critical in the global context, based on the gradient of the asymptotic decider in each element that shares the face. However, as defined, the method of Weber et al. contains an error, and can lead to incorrect results. In this work we correct the error.

Accurate and fast 3D object detection from point clouds is a key task in autonomous driving. Existing one-stage 3D object detection methods can achieve real-time performance, however, they are dominated by anchor-based detectors which are inefficient and require additional post-processing. In this paper, we eliminate anchors and model an object as a single point--the center point of its bounding box. Based on the center point, we propose an anchor-free CenterNet3D network that performs 3D object detection without anchors. Our CenterNet3D uses keypoint estimation to find center points and directly regresses 3D bounding boxes. However, because inherent sparsity of point clouds, 3D object center points are likely to be in empty space which makes it difficult to estimate accurate boundaries. To solve this issue, we propose an extra corner attention module to enforce the CNN backbone to pay more attention to object boundaries. Besides, considering that one-stage detectors suffer from the discordance between the predicted bounding boxes and corresponding classification confidences, we develop an efficient keypoint-sensitive warping operation to align the confidences to the predicted bounding boxes. Our proposed CenterNet3D is non-maximum suppression free which makes it more efficient and simpler. We evaluate CenterNet3D on the widely used KITTI dataset and more challenging nuScenes dataset. Our method outperforms all state-of-the-art anchor-based one-stage methods and has comparable performance to two-stage methods as well. It has an inference speed of 20 FPS and achieves the best speed and accuracy trade-off. Our source code will be released at https://github.com/wangguojun2018/CenterNet3d., 13 pages, 5 figures

This paper revisits the analysis of the well-known infeed effect on transmission lines distance protection. A new adaptive algorithm to overcome this drawback is proposed, which requires solely impedance data and the operational status of power apparatus to perform overreaching distance zones settings. A comparison of the proposed strategy and the traditional one is performed. The obtained results demonstrate that the proposed settings ensure the correct operation of overreaching zones. Thereby, the backup coverage is improved significantly, besides avoiding distance zones overlapping between adjacent lines. It reveals the proposed strategy usefulness and value from the practical point of view, since it can be implemented with technology readily available on the market.

Object detection is the most critical and foundational sensing module for the autonomous movement platform. However, most of the existing deep learning solutions are based on GPU servers, which limits their actual deployment. We present an efficient multi-sensor fusion based object detection model that can be deployed on the off-the-shelf edge computing device for the vehicle platform. To achieve real-time target detection, the model eliminates a large number of invalid point clouds through ground filtering algorithm, and then adds texture information (fused from camera image) through point cloud coloring to enhance features. The proposed PV-EncoNet efficiently encodes both the spatial and texture features of each colored point through point-wise and voxel-wise encoding, and then predicts the position, heading and class of the objects. The final model can achieve about 17.92 and 24.25 Frame per Second (FPS) on two different edge computing platforms, and the detection accuracy is comparable with the state-of-the-art models on the KITTI public dataset (i.e., 88.54% for cars, 71.94% for pedestrians and 73.04% for cyclists). The robustness and generalization ability of the PV-EncoNet for the 3D colored point cloud detection task is also verified by deploying it on the local vehicle platform and testing it on real road conditions.

An integrated zero common mode voltage (ZCMV) modulation algorithm is developed in this research for dual-parallel neutral-point-clamped (NPC) inverters treated as an integrated system. While the conventional methods achieve CMV elimination with the cost of worse harmonic performance, the proposed method guarantees zero CMV and better current quality simultaneously by taking advantage of the extra space vectors provided by paralleling. Specially designed switching sequences are developed to maintain a balanced neutral point of DC-bus and ensure the averaged circulating current being zero, which is critical to the parallel operation and normal function of NPC inverters. In addition, although the switching sequence design is complicated, a simple approach is proposed and implemented on a commonly used digital signal processor (DSP). A laboratory prototype is also developed and used to test the system performance under steady-state conditions and dynamic process in grid-connected operation. Compared with conventional ZCMV modulation, experimental results verify the effectiveness of the integrated modulation in eliminating CMV, in addition to the dramatically reduced output current distortion.

Overlapping community detection is essential for revealing the hidden structure of complex networks. In this work, we present an overlapping community detection algorithm that selects community centers adaptively based on density peaks. The proposed algorithm, called the density-peak-based overlapping community detection (DPOCD) algorithm, defines point link strength and edge link strength to construct distance matrix. Unlike the density peaks clustering algorithm, by which cluster centers are selected manually, the DPOCD algorithm uses the linear fitting method to select community centers. To evaluate the feasibility of the presented algorithm, we compared it with other advanced methods on artificial synthetic network and real complex network datasets. The experimental results demonstrate that our method achieves excellent performance in large-scale complex networks and the robustness of the algorithm.

The conventional maximum power point tracking (MPPT) controllers are unable to track the global maximum power point (GMPP) during partial shading conditions (PSCs). As a result, many optimization strategies have been used to track the GMPP. Optimization approaches, on the other hand, are iterative methods that cannot distinguish uniform shading conditions (USCs) from PSCs. In this paper, a new partial shading detection approach has been hybridized with the new modified rat swarm optimization algorithm (MRSO). It successfully distinguishes USCs from PSCs in two samples and triggers the MRSO only when the PSC is detected. Consequently, it avoids the excessive global peak search during the USCs, which improves the tracking time for USCs without an unnecessary scan of the entire P–V curve. Furthermore, the proposed MRSO, is simple to implement with simple tuning parameters and fast tracking speed for PSCs. The proposed method has been experimentally validated on a boost converter with a sampling time of 0.05 s. The experimental results showed the successful implementation of the proposed method with an average tracking time for uniform and PSCs of 0.42 s with an average steady-state efficiency of 99.8%. Subsequently, a comparison with state-of-the-art methods in this domain has been provided to assess the efficacy of the proposed method.

A fuzzy first order and second moment method (FFOSM) is proposed to efficiently estimate time-independent and time-dependent failure credibility in the presence of fuzzy uncertainty. For the time-independent linear performance function with independently, regularly and identically distributed fuzzy inputs, the analytical relationship is firstly derived between the failure credibility and fuzzy safety index, and the relation form is established between fuzzy safety index and fuzzy first two moments of the performance function. Secondly, in the standard space of fuzzy inputs, the minimum infinite norm distance from the coordinate origin to the linear limit state surface is analytically derived, and the point with the smallest infinite norm distance located on the limit state surface is defined as the fuzzy design point. Based on this definition, the geometric and physical meanings are explained for the fuzzy safety index and fuzzy design point, and the fuzzy first order and second moment method for time-independent failure credibility analysis is established for both linear and nonlinear performance function. Thirdly, for time-dependent performance functions, the equivalence is proved between time-dependent fuzzy safety index and the minimum value of transient fuzzy safety indices, on which the iteration steps of fuzzy first order and second moment method is designed for time-dependent fuzzy safety index and failure credibility estimation. Since the proposed fuzzy first order and second moment method is an approximately analytical approach, it has higher efficiency than the fuzzy simulation method and the cut level optimization method. Finally, the effectiveness and applicability of the proposed method are demonstrated by different examples.

3D tracking in point cloud is a core competence of autonomous robots to perceive and forecast the environment. How to initialize bounding box seeds and optimize their position and orientation are very crucial for 3D object tracking in point clouds. Nevertheless, existing methods mainly resort to developing a powerful classifier based on the initial bounding box seeds. In this work, we propose an end-to-end deep supervised descent method (SDM), which seamlessly integrates multiple seeds generation for the initialization of seeds and sequential updates for the estimation of accurate result. Specifically, we start with transforming the SDM iterative process into a trainable recurrent module. It explicitly learns a series of descent directions in the parameter space, to gradually optimize the initial seeds. Moreover, to alleviate drifting of this process, we initialize multiple seeds based on aggregated point sets generated by the deep Hough voting. Besides, a discrimination module is introduced to determine the bounding box with the highest score as the final result. Importantly, a specific multi-task loss is proposed to train our model in an end-to-end way. Experiments on KITTI, PandaSet and Waymo datasets show that our method could achieve significant improvements (up to 11.2\% in success ratio) as compared to state-of-the-art trackers.

Stochastic point location deals with the problem of finding a target point on a real line through a learning mechanism (LM) with the stochastic environment (SE) offering directional information. The SE can be further categorized into an informative or deceptive one, according to whether p is above 0.5 or not, where p is the probability of providing a correct suggestion of a direction to LM. Several attempts have been made for LM to work in both types of environments, but none of them considers a dynamically changing environment where p varies with time. A dynamic dual environment involves fierce changes that frequently cause its environment to switch from an informative one to a deceptive one, or vice versa. This article presents a novel weak estimator-based adaptive step search solution, to enable LM to track the target in a dynamic dual environment, with the help of a weak estimator. The experimental results show that the proposed solution is feasible and efficient.

Researchers have proposed many novel methods to detect abnormal taxi trajectories. However, most of the existing methods usually adopt a counting-based strategy, which may cause high false positives due to imprecisely identifying diverse trajectories as anomalies and therefore, they need the support of large-scale historical trajectories to work properly. To improve detection precision and efficiency, in this article, we propose STR, an online abnormal taxi trajectory detection method based on spatio-temporal relations. The basic principle behind STR is that given the displacement from the source point to a testing point, if the driving time and driving distance are not within the normal ranges, the point is identified as anomalous. To learn the two normal ranges for driving time and driving distance, STR defines two spatio-temporal models which characterize the relationship between displacement and driving distance/driving time. To improve detection efficiency, STR reduces the number of models that need to be learned by making full use of the similarity of transportation modes in different time periods and neighboring areas. The effectiveness and performance of STR are evaluated on real-world taxi trajectories. The experiment results show that compared with counting-based methods, STR achieves greater precision by reducing false positives. Furthermore, STR is more efficient than its counterparts and is suitable for online detection.

This article addresses the trajectory consensus problem of coordinating the trajectories of vehicles at multiple future time points. The objective is the consensus of the geometry of the vehicles' planned trajectories. The geometric feature of trajectories is parameterized by a set of trajectory states defined as required lengths along the trajectory to reduce the distance to its ending point to specific values. To solve this special consensus problem involving coupled state variables, the conventional consensus model is extended by attaching it to a mapping from the state variables to the trajectory's geometry. This mapping is established using a homotopic structure that creates a compact and efficient form for the mapping. The geometry of the homotopic structure is based on the shapes of its envelopes, and the elements in the structure are derived from their deformation. Through a homotopic search in the structure, an asymptotic consensus of trajectory states is achieved. Simulation results show the proposed coupled state consensus method can achieve better performance on the consensus of multiple vehicles than the conventional isolated state consensus method.

Traffic prediction, as a core component of intelligent transportation systems (ITS), has been investigated thoroughly in the literature. Nevertheless, timely accurate traffic prediction still remains an open challenge due to the nonlinearities and complex patterns of traffic flows. In addition, most of the existing traffic prediction methods focus on grid-based computing problems (e.g., crowd in-out flow prediction) and point-based computing problems (e.g., traffic detector data prediction), ignoring the segment-based traffic prediction tasks. In this study, we propose an attention-based spatiotemporal graph attention network (AST-GAT) for segment-level traffic speed prediction. In particular, a multi-head graph attention block is designed to capture the spatial dependencies among road segments. Then, a component fusion block is built for speed, volume, and weather information integration. Finally, an attention-based Long short-term memory (LSTM) block is constructed for temporal dependency learning as well as segment-based speed prediction. Experiments on a real-world dataset from Highways England demonstrate that the proposed AST-GAT model outperforms the state-of-the-art baselines, providing an efficient tool for segment-based traffic prediction and therefore filling the gap between point-based and grid-based predictions.

In this paper, the estimation problem of Toolface is investigated for the dynamic point-the-bit rotary steerable system (DPRSS), and it is essentially a nonlinear filtering problem under strong interference. Firstly, the DPRSS is modeled by a continuous-time nonlinear system which involves polynomial nonlinearities and strong interference whose amplitude is much larger than that of system states. By employing the Carleman approximation approach, a linear parameter varying system is derived from the polynomial nonlinear system, and a novel polynomial filter is constructed. Subsequently, several sufficient conditions in terms of parameter-dependent linear matrix inequalities (PDLMIs) are obtained to ensure the input-to-state stability of the filtering error system. Furthermore, the filter parameter can be calculated by solving PDLMIs through the sum-of-squares decomposition method. Finally, an experimental study on the DPRSS prototype is provided to show the effectiveness and applicability of the developed filtering scheme.

Perception techniques for autonomous driving should be adaptive to various environments. In the case of traffic line detection, an essential perception module, many condition should be considered, such as number of traffic lines and computing power of the target system. To address these problems, in this paper, we propose a traffic line detection method called Point Instance Network (PINet); the method is based on the key points estimation and instance segmentation approach. The PINet includes several stacked hourglass networks that are trained simultaneously. Therefore the size of the trained models can be chosen according to the computing power of the target environment. We cast a clustering problem of the predicted key points as an instance segmentation problem; the PINet can be trained regardless of the number of the traffic lines. The PINet achieves competitive accuracy and false positive on the TuSimple and Culane datasets, popular public datasets for lane detection. Our code is available at https://github.com/koyeongmin/PINet_new, Submitted to "IEEE Transactions on Intelligent Transportation Systems"

Most real-world networks are time-varying, and many are subject to the stochastic functioning of their nodes and edges. Examples can be seen in the human brain undergoing an epileptic seizure, spontaneous infection and recovery in epidemics, and intermittent functioning of devices in the Internet of Things. Moreover, such networks are becoming increasingly large due to rapid technological advances. However, little has been done to study time-varying, large-scale, stochastic networks (SNs) from a reliability engineering perspective. Toward this goal, this article develops a fault-tolerance model for a type of time-varying network in which nodes (and/or edges) stochastically switch between active and inactive states. It considers fault tolerance from a global connectivity point of view, which has applications in many natural and engineered networks. Specifically, this article presents a Markov chain framework that models the dynamic behavior of nodes and allows for the computation of quantitative measures, including availability and time-to-failure metrics. To accommodate large-scale networks and emphasize global connectivity, this framework utilizes percolation theory, which has recently been of interest in the reliability engineering discipline, to characterize network failure. This article makes several contributions: it proposes a Markov chain framework for computing fault-tolerance metrics that is tractable for large-scale networks, it shows the existence of a phase transition in network availability of a time-varying SN, and it accounts for finite-size effects of percolation in the fault-tolerance model. The proposed methodology is applied to Erdos-Renyi random graphs and a real, large-scale power grid. Experimental results provide insights into network design, maintenance, and failure prevention of time-varying SNs.

In this work, we propose two lightweight access point (AP) localization and selection schemes, AP-Cov and IAP-Cov, in IEEE 802.11-enabled IoT networks for reducing handover delay and maintaining uninterrupted connectivity during movement. The proposed scheme AP-Cov consists of two phases – localization of APs and a priori selection of APs in the direction of mobility. In the localization phase, an IoT device exploits the features of Neighbor Report Request (NRR) and Beacon Report Request (BRR) of IEEE 802.11k to get the nearby APs’ informations along with their location and uses simple algebra to compute the location of next APs beforehand, instead of using heavyweight processing in resource-constrained IoT networks. In the AP selection phase, a linear optimization model is formulated to select the optimal AP for subsequent association. In IAP-Cov, a broadcast sequence of neighbor IoTs is proposed for reducing the number of broadcasts. We implement the schemes in NS-3 and compare performance with the baseline standard, which shows that AP-Cov detects the availability of APs with 98.625%, 96.5% accuracy, improves accuracy over message complexity by 23%, 78% and reduces handover by 36.37%, 67.52% in constant velocity and random velocity mobility model, respectively. The evaluation of computational complexity shows that the proposed schemes are lightweight too. IAP-Cov reduces broadcasts and delay by 49%, 77.36% and 6%, 25% compared to AP-Cov using the constant and random velocity mobility models, respectively.

This article develops an equivalent circuit-based model to perform power and emission tracing in power grids. By relying on the proposed model, a power network can be readily converted into a series of equivalent acyclic circuits so that the contributions of generators to a specific load can be clearly and unequivocally traced from a circuit point of view without making any assumptions on how nodal power inflows contribute to the outflows. The effectiveness of the proposed method is discussed through both power flow and optimal power flow simulations on three case studies, including a simple two-generator network, and the IEEE standard 14-bus and 118-bus systems. Furthermore, the proposed power flow tracing method is used in estimating the electricity-associated emissions from the customer side.

Homogeneous magnetic field is widely used in various applications, and Helmholtz and Merritt coils are the most commonly used homogeneous field generators. However, only the field homogeneity at the center point is concerned in their design, which leads to restriction for most applications where a certain volume of homogeneous field is required. This indicates that traditional coil configurations can be further optimized. Based upon a comprehensive definition of homogeneous field, improved three-coil and four-coil configurations are proposed in this paper. Practical formulae with normalized coil parameters are given to provide a convenient tool for designers. These formulae establish relationships between coil parameters and the required homogeneous field. The accuracy of the formulae is verified by the finite-element analysis. Comparisons with Merritt coils show that, when getting the same homogeneous field, the improved coils can reduce both power loss and conductor mass by up to 24.8%. Through a comparison among main coil configurations, the improved four-coil configuration is recommended for homogeneous magnetic field generation. For high-intensity magnetic field applications, the winding cross-section effect is analyzed. At last, experiments are performed to verify the theoretical analysis, and the reason why the improved coils have better performance than traditional ones is revealed.

The literature on the subject of frequency estimation algorithms has discussed the use of interpolated discrete Fourier transform (IpDFT) for the unbalanced/balanced three-phase voltage signal in a power system. It is difficult to estimate frequency of the unbalanced signal with high accuracy since the unknown parameters of the unbalanced signal make the spectrum different from the real-valued sinusoid signal. Moreover, the spectral leakage of the spectrum of the unbalanced signal also brings large estimation errors when the acquired signal cycles become very small. In this paper, we propose a two11 point iterative IpDFT algorithm for frequency estimation of the unbalanced/balanced three-phase voltage signal. We decompose the unbalanced signal into a real-valued sinusoid signal, and then search the system frequency iteratively with the minimum error by bisection method. Both long- and short- range leakages are compensated to estimate the frequency accurately. Simulation results prove the effectiveness of our method, compared with other iterative/noniterative IpDFT methods.

Logic locking has emerged as a prominent key-driven technique to protect the integrity of integrated circuits. However, novel machine-learning-based attacks have recently been introduced to challenge the security foundations of locking schemes. These attacks are able to recover a significant percentage of the key without having access to an activated circuit. This paper address this issue through two focal points. First, we present a theoretical model to test locking schemes for key-related structural leakage that can be exploited by machine learning. Second, based on the theoretical model, we introduce D-MUX: a deceptive multiplexer-based logic-locking scheme that is resilient against structure-exploiting machine learning attacks. Through the design of D-MUX, we uncover a major fallacy in existing multiplexer-based locking schemes in the form of a structural-analysis attack. Finally, an extensive cost evaluation of D-MUX is presented. To the best of our knowledge, D-MUX is the first machine-learning-resilient locking scheme capable of protecting against all known learning-based attacks. Hereby, the presented work offers a starting point for the design and evaluation of future-generation logic locking in the era of machine learning., Comment: Accepted at IEEE TCAD 2021

To meet the urgent demands in a wide range of geospatial applications, such as road management, intelligent transportation systems, road safety evaluation, and traffic accident analysis, automatic and accurate extraction of 3D roads and associated geometric parameters from point clouds is receiving wide attention. In this paper, we propose an accurate 3D road boundary extraction and vectorization method to bridge the gap from unstructured mobile laser scanning (MLS) point clouds to the vector-based representation of road boundary. Firstly, we propose a supervoxel generation method to extract candidate curbs with fine border preservation and high computation efficiencies. Then the candidate curb supervoxels are recognized and clustered to produce continuous road boundary segments with a contracted distance clustering strategy. Finally, the vectorized road boundary is represented by fitting, tracking, and completion from the extracted road boundary segments, resulting in road geometric parameters including boundary location, road widths, turning radius, and slopes. The performance of the proposed method was evaluated on two large-scale datasets collected in urban and industrial areas. Comprehensive experiments reveal that the proposed method is robust to various road shapes and point densities, in terms of precision of 95.0% and recall of 91.0%, respectively.

With the evolution of electronic devices, such as 3D cameras, addressing the challenges of text localization in 3D video (e.g., for indexing) is increasingly drawing the attention of the multimedia and video processing community. Existing methods focus on 2D video and their performance in the presence of the challenges in 3D video, such as shadow areas associated with text and irregularly sized and shaped text, degrades. This paper proposes the first approach that successfully addresses the challenges of 3D video in addition to those of 2D. It employs a number of innovations, among which, the first is the Generalized Gradient Vector Flow (GGVF) for dominant points detection. The second is the Wavefront concept for text candidate point detection from those dominant points. In addition, an Adaptive B-Spline Polygon Curve Network (ABS-Net) is proposed for accurate text localization in 3D videos by constructing tight fitting bounding polygons using text candidate points. Extensive experiments on custom (3D video) and standard datasets (2D video and scene text) show that the proposed method is practical and useful, and overall outperforms existing state-of-the-art methods.

The existing mission planning models for conventional agile Earth observation satellites assuming stable push-broom imaging cannot be directly adapted to newly developed superagile Earth observation satellites (SA-EOS) with dynamic imaging capabilities. To guarantee the application efficiency of SA-EOS, a novel mission planning modeling method for multipoint target imaging within a single pass (MTI-SP) is proposed. First, a two-step preprocessing method for point targets based on the “nonalong-track” characteristic of SA-EOS converts multiple point targets into imaging strips as an atomic mission for further planning. Then, a triple of decision variables is defined, i.e., the index of the imaging sequence of multiple strips, indices of the push-broom direction of the strips, and normalization coefficients of the imaging time of each endpoint of the strips, on the basis of the one-to-one correspondence between the triple and the imaging time. Third, an optimal MTI-SP mission planning model with two objective functions, namely maximizing the mission coverage benefit (MCB) and minimizing the mission completion time (MCT), is established by considering the imaging time window and attitude transition time. An improved particle swarm optimization algorithm is used for the MTI-SP solution. The results of comparison experiments indicate that the proposed model can achieve the maximum MCB with lower computational consumption. Compared with the two fixed push-broom sequence models and the independent point targets model, the MCT of the proposed model is improved by 47.1%, 24.56%, and 89.45%, respectively. The experiment results show that the proposed modeling method can be further applied in ground operational systems of SA-EOS.